AI Agents & Frameworks
Autonomous agents and the frameworks to build them — orchestration, planning, multi-agent systems. Tracked daily with star velocity from real snapshots.
Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.
Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifth.
A modular UX, design, and product optimisation system for turning AI-built interfaces into production-grade apps, turning proven principles into enforceable constraints that reduce friction, build trust, and drive action. Works with Claude, Codex, Cursor + all other agentic AI models.
Engineering workflows for AI coding agents or flesh engineers. It helps absorb silent base-model quality drift.
from vibe coding to agentic engineering - practice makes gemini perfect
Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).
Agentic runtime in Rust — persistent, supervised agents. Self-hosted, local-first, zero telemetry. Apache 2.0.
A local dashboard to manage AI coding agent skills — sync, install, and organize skills across OpenClaw, Cursor, Claude Code, and more.
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
Skill to generate the knowledge vault for projects using the Ralph loop
Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.
Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted
Desktop automation CLI for AI agents. Fast native Rust CLI.
Kubernetes-native sandbox platform to run AI agents, coding assistants and harnesses.
Takeover your voice assistant with powerful agent
macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.
Unofficial Google-Health-CLI for the Google Health API, written in Go
Podplane is a Kubernetes distribution & PaaS you can deploy in a few minutes to your AWS, Google Cloud, or Proxmox VE environment
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.
Coral is an open-source, local-first session bridge that lets AI agents borrow a user's already-authenticated browser sessions on a per-site, per-action, fully audited basis.
Your agents run loops. Brigade keeps the receipts. Local control plane: share MCP, tools, and memory across harnesses; prove with file receipts; improve only from real exit codes. No daemon, no lock-in.
Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pickpocketing) via YOLOv8 + BiLSTM + multi-agent reasoning — zero new hardware, privacy-first, no facial recognition.
Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.
gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots
Track brand mentions across Perplexity, ChatGPT, Claude & Gemini AI search inside any MCP agent. GEO scoring, share of voice, citations, competitors.